Patents by Inventor Guillermo Sapiro
Guillermo Sapiro has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11813054Abstract: The subject matter described herein includes methods, systems, and computer readable media for conducting an automatic assessment of postural control of a subject. According to one aspect, a method occurs at a computing platform including a processor and memory. The method includes displaying a stimulus to which a subject responds, capturing facial image data of the subject, analyzing the facial image data to determine a frequency of head displacement information associated with the subject, using the head displacement information to derive postural control assessment data, and determining that the postural control assessment data is indicative of a neurodevelopmental or neuropsychiatric disorder associated with the subject.Type: GrantFiled: November 8, 2019Date of Patent: November 14, 2023Assignee: Duke UniversityInventors: Geraldine Dawson, Guillermo Sapiro, Jordan Hashemi
-
Patent number: 11771389Abstract: A volumetric segmentation method is disclosed for brain region analysis, in particular but not limited to, regions of the basal ganglia such as the subthalamic nucleus (STN). This serves for visualization and localization within the sub-cortical region of the basal ganglia, as an example of prediction of a region of interest for deep brain stimulation procedures. A statistical shape model is applied for variation modes of the STN, or the corresponding regions of interest, and its predictors on high-quality training sets obtained from high-field, e.g., 7T, MR imaging. The partial least squares regression (PLSR) method is applied to induce the spatial relationship between the region to be predicted, e.g., STN, and its predictors. The prediction accuracy for validating the invention is evaluated by measuring the shape similarity and the errors in position, size, and orientation between manually segmented STN and its predicted one.Type: GrantFiled: December 29, 2020Date of Patent: October 3, 2023Assignee: Owl Navigation, Inc.Inventors: Guillermo Sapiro, Noam Harel, Yuval Duchin, Jin Young Kim
-
Publication number: 20230293130Abstract: A volumetric segmentation method is disclosed for brain region analysis, in particular but not limited to, regions of the basal ganglia such as the subthalamic nucleus (STN). This serves for visualization and localization within the sub-cortical region of the basal ganglia, as an example of prediction of a region of interest for deep brain stimulation procedures. A statistical shape model is applied for variation modes of the STN, or the corresponding regions of interest, and its predictors on high-quality training sets obtained from high-field, e.g., 7 T, MR imaging. The partial least squares regression (PLSR) method is applied to induce the spatial relationship between the region to be predicted, e.g., STN, and its predictors. The prediction accuracy for validating the invention is evaluated by measuring the shape similarity and the errors in position, size, and orientation between manually segmented STN and its predicted one.Type: ApplicationFiled: April 27, 2023Publication date: September 21, 2023Inventors: Guillermo Sapiro, Noam Harel, Yuval Duchin, Jin Young Kim
-
Patent number: 11705632Abstract: Systems and methods for designing, optimizing, patterning, forming, and manufacturing symphotic structures are described herein. A symphotic structure may be formed by identifying a continuous refractive index distribution calculated to convert each of a plurality of input reference waves to a corresponding plurality of output object waves. The continuous refractive index distribution can be modeled as a plurality of subwavelength voxels. The system can calculate a symphotic pattern as a three-dimensional array of discrete dipole values to functionally approximate the subwavelength voxels. A symphotic structure may be formed with a volumetric distribution of dipole structures. A dipole value, such as a dipole moment (direction and magnitude) of each dipole is selected for the volumetric distribution to convert a plurality of input reference waves to a target plurality of output object waves.Type: GrantFiled: September 21, 2018Date of Patent: July 18, 2023Inventors: David R. Smith, Guillermo Sapiro, Daniel L. Marks, Patrick Bowen, Roberto Zecca, Okan Yurduseven, Jonah N. Gollub
-
Publication number: 20230136320Abstract: A system and method are provided for creating magnetic resonance (MR) images with reduced motion artifacts from the MR data from which the images are produced. The method includes selecting a candidate image from a plurality of candidate images reconstructed from the MR data. The method also includes registering the candidate image to a reference image, comparing the candidate image to a consistency map, and, based on comparing the candidate image using the consistency map, selecting a blending algorithm. The method also includes generating a blended image using the blending algorithm and the candidate image and repeating these steps for each candidate image. The method also includes performing a Fourier aggregation to generate a combined image and displaying the combined image with reduced motion artifacts compared to the plurality of candidate images.Type: ApplicationFiled: September 19, 2022Publication date: May 4, 2023Inventors: Oren Solomon, Noam Harel, Guillermo Sapiro, Edward Auerbach, Steen Moeller, Remi Patriat, Henry Braun, Tara Palnitkar
-
Patent number: 11580874Abstract: The subject matter described herein includes methods, systems, and computer readable media for automated attention assessment. According to one method, a method for automated attention assessment includes obtaining head and iris positions of a user using a camera while the user watches a display screen displaying a video containing dynamic region-based stimuli designed for identifying a neurodevelopmental and/or psychiatric (neurodevelopmental/psychiatric) disorder; analyzing the head and iris positions of the user to detect attention assessment information associated with the user, wherein the attention assessment information indicates how often and/or how long the user attended to one or more regions of the display screen while watching the video; determining that the attention assessment information is indicative of the neurodevelopmental/psychiatric disorder; and providing, via a communications interface, the attention assessment information, a diagnosis, or related data.Type: GrantFiled: November 8, 2019Date of Patent: February 14, 2023Assignee: Duke UniversityInventors: Guillermo Sapiro, Geraldine Dawson, Matthieu Bovery, Jordan Hashemi
-
Publication number: 20210374953Abstract: A method for automated detection of cervical pre-cancer includes: providing at least one cervigram; pre-processing the at least one cervigram; extracting features from the at least one pre-processed cervigram; and classifying the at least one cervigram as negative or positive for cervical pre-cancer based on the extracted features.Type: ApplicationFiled: October 4, 2019Publication date: December 2, 2021Inventors: Mercy Asiedu, Nirmala Ramanujam, Guillermo Sapiro
-
Patent number: 11158403Abstract: The subject matter described herein includes methods, systems, and computer readable media for automated behavioral assessment. According to one aspect, a method for automated behavioral assessment is provided. The method occurs at a computing platform including a processor and memory. The method includes providing at least one stimulus for eliciting a response from a user. The method also includes obtaining, using a camera or sensor communicatively coupled to the computing platform, the at least one response. The method also includes determining, using the at least one response, a behavioral assessment associated with the user.Type: GrantFiled: April 28, 2016Date of Patent: October 26, 2021Assignee: Duke UniversityInventors: Guillermo Sapiro, Helen Egger, Geraldine Dawson, Robert Calderbank, Jeffrey Baker, Kimberly Carpenter, Adrianne Harris, Kathleen Campbell, Jordan Hashemi, Qiang Qiu, Mariano Tepper
-
Publication number: 20210118549Abstract: A volumetric segmentation method is disclosed for brain region analysis, in particular but not limited to, regions of the basal ganglia such as the subthalamic nucleus (STN). This serves for visualization and localization within the sub-cortical region of the basal ganglia, as an example of prediction of a region of interest for deep brain stimulation procedures. A statistical shape model is applied for variation modes of the STN, or the corresponding regions of interest, and its predictors on high-quality training sets obtained from high-field, e.g., 7T, MR imaging. The partial least squares regression (PLSR) method is applied to induce the spatial relationship between the region to be predicted, e.g., STN, and its predictors. The prediction accuracy for validating the invention is evaluated by measuring the shape similarity and the errors in position, size, and orientation between manually segmented STN and its predicted one.Type: ApplicationFiled: December 29, 2020Publication date: April 22, 2021Inventors: Guillermo Sapiro, Noam Harel, Yuval Duchin, Jinyoung Kim
-
Patent number: 10885149Abstract: A volumetric segmentation method is disclosed for brain region analysis, in particular but not limited to, regions of the basal ganglia such as the subthalamic nucleus (STN). This serves for visualization and localization within the sub-cortical region of the basal ganglia, as an example of prediction of a region of interest for deep brain stimulation procedures. A statistical shape model is applied for variation modes of the STN, or the corresponding regions of interest, and its predictors on high-quality training sets obtained from high-field, e.g., 7T, MR imaging. The partial least squares regression (PLSR) method is applied to induce the spatial relationship between the region to be predicted, e.g., STN, and its predictors. The prediction accuracy for validating the invention is evaluated by measuring the shape similarity and the errors in position, size, and orientation between manually segmented STN and its predicted one.Type: GrantFiled: March 13, 2017Date of Patent: January 5, 2021Assignee: Owl Navigation, Inc.Inventors: Guillermo Sapiro, Noam Harel, Yuval Duchin, Jin Young Kim
-
Publication number: 20190109379Abstract: Systems and methods for designing, optimizing, patterning, forming, and manufacturing symphotic structures are described herein. A symphotic structure may be formed by identifying a continuous refractive index distribution calculated to convert each of a plurality of input reference waves to a corresponding plurality of output object waves. The continuous refractive index distribution can be modeled as a plurality of subwavelength voxels. The system can calculate a symphotic pattern as a three-dimensional array of discrete dipole values to functionally approximate the subwavelength voxels. A symphotic structure may be formed with a volumetric distribution of dipole structures. A dipole value, such as a dipole moment (direction and magnitude) of each dipole is selected for the volumetric distribution to convert a plurality of input reference waves to a target plurality of output object waves.Type: ApplicationFiled: September 21, 2018Publication date: April 11, 2019Inventors: David R. Smith, Guillermo Sapiro, Daniel L. Marks, Patrick Bowen, Roberto Zecca, Okan Yurduseven, Jonah N. Gollub
-
Patent number: 10146991Abstract: Methods and systems for large-scale face recognition. The system includes an electronic processor to receive at least one image of a subject of interest and apply at least one subspace model as a splitting binary decision function on the at least one image of the subject of interest. The electronic processor is further configured to generate at least one binary code from the at least one splitting binary decision function. The electronic processor is further configured to apply a code aggregation model to combine the at least one binary codes generated by the at least one subspace model. The electronic processor is further configured to generate an aggregated binary code from the code aggregation model and use the aggregated binary code to provide a hashing scheme.Type: GrantFiled: June 10, 2016Date of Patent: December 4, 2018Assignee: Duke UniversityInventors: Guillermo Sapiro, Qiang Qiu, Alexander Bronstein
-
Patent number: 9998666Abstract: System and Method for automatically removing blur and noise in a plurality of digital images. The system comprises an electronic processor configured to receive the plurality of digital images, perform motion estimation and motion compensation to align the plurality of digital images, determine an alignment of the plurality of digital images with respect to a reference frame, generate a consistency map based on the alignment of the plurality of digital images with respect to the reference frame, combine the plurality of digital images aligned with respect to the reference frame in the Fourier domain using a quality of alignment information from the consistency map to generate an aggregated frame, and apply a post-processing filter to enhance the quality of the aggregated frame.Type: GrantFiled: August 26, 2016Date of Patent: June 12, 2018Assignee: Duke UniversityInventors: Guillermo Sapiro, Mauricio Delbracio
-
Publication number: 20170193161Abstract: A volumetric segmentation method is disclosed for brain region analysis, in particular but not limited to, regions of the basal ganglia such as the subthalamic nucleus (STN). This serves for visualization and localization within the sub-cortical region of the basal ganglia, as an example of prediction of a region of interest for deep brain stimulation procedures. A statistical shape model is applied for variation modes of the STN, or the corresponding regions of interest, and its predictors on high-quality training sets obtained from high-field, e.g., 7T, MR imaging. The partial least squares regression (PLSR) method is applied to induce the spatial relationship between the region to be predicted, e.g., STN, and its predictors. The prediction accuracy for validating the invention is evaluated by measuring the shape similarity and the errors in position, size, and orientation between manually segmented STN and its predicted one.Type: ApplicationFiled: March 13, 2017Publication date: July 6, 2017Inventors: Guillermo Sapiro, Noam Harel, Yuval Duchin, Jinyoung Kim
-
Patent number: 9600778Abstract: A volumetric segmentation method is disclosed for brain region analysis, in particular but not limited to, regions of the basal ganglia such as the subthalamic nucleus (STN). This serves for visualization and localization within the sub-cortical region of the basal ganglia, as an example of prediction of a region of interest for deep brain stimulation procedures. A statistical shape model is applied for variation modes of the STN, or the corresponding regions of interest, and its predictors on high-quality training sets obtained from high-field, e.g., 7T, MR imaging. The partial least squares regression (PLSR) method is applied to induce the spatial relationship between the region to be predicted, e.g., STN, and its predictors. The prediction accuracy for validating the invention is evaluated by measuring the shape similarity and the errors in position, size, and orientation between manually segmented STN and its predicted one.Type: GrantFiled: June 27, 2014Date of Patent: March 21, 2017Assignee: Surgical Information Sciences, Inc.Inventors: Guillermo Sapiro, Noam Harel, Yuval Duchin, Jinyoung Kim
-
Publication number: 20170076143Abstract: Methods and systems for large-scale face recognition. The system includes an electronic processor to receive at least one image of a subject of interest and apply at least one subspace model as a splitting binary decision function on the at least one image of the subject of interest. The electronic processor is further configured to generate at least one binary code from the at least one splitting binary decision function. The electronic processor is further configured to apply a code aggregation model to combine the at least one binary codes generated by the at least one subspace model. The electronic processor is further configured to generate an aggregated binary code from the code aggregation model and use the aggregated binary code to provide a hashing scheme.Type: ApplicationFiled: June 10, 2016Publication date: March 16, 2017Inventors: Guillermo Sapiro, Qiang Qiu, Alexander Bronstein
-
Publication number: 20170064204Abstract: System and Method for automatically removing blur and noise in a plurality of digital images. The system comprises an electronic processor configured to receive the plurality of digital images, perform motion estimation and motion compensation to align the plurality of digital images, determine an alignment of the plurality of digital images with respect to a reference frame, generate a consistency map based on the alignment of the plurality of digital images with respect to the reference frame, combine the plurality of digital images aligned with respect to the reference frame in the Fourier domain using a quality of alignment information from the consistency map to generate an aggregated frame, and apply a post-processing filter to enhance the quality of the aggregated frame.Type: ApplicationFiled: August 26, 2016Publication date: March 2, 2017Inventors: Guillermo Sapiro, Mauricio Delbracio
-
Patent number: 9412076Abstract: A volumetric segmentation method is disclosed for brain region analysis, in particular but not limited to, regions of the basal ganglia such as the subthalamic nucleus (STN). This serves for visualization and localization within the sub-cortical region of the basal ganglia, as an example of prediction of a region of interest for deep brain stimulation procedures. A statistical shape model is applied for variation modes of the STN, or the corresponding regions of interest, and its predictors on high-quality training sets obtained from high-field, e.g., 7 T, MR imaging. The partial least squares regression (PLSR) method is applied to induce the spatial relationship between the region to be predicted, e.g., STN, and its predictors. The prediction accuracy for validating the invention is evaluated by measuring the shape similarity and the errors in position, size, and orientation between manually segmented STN and its predicted one.Type: GrantFiled: June 27, 2014Date of Patent: August 9, 2016Assignee: Surgical Information Sciences, Inc.Inventors: Guillermo Sapiro, Noam Harel
-
Patent number: 9031312Abstract: A computerized inspection system is described for detecting the presence of non-uniformity defects and providing output indicative of a severity of each type of non-uniformity defect. Techniques are described that increase the throughput of the inspection system. Algorithmic and hardware approaches are described to significantly decrease the average amount of time required to inspect a given quantity of material that is expected to be mostly uniform. The techniques described herein involve dynamic selection of which image features to compute by starting with a base feature set and only triggering additional feature computations as needed until the features are sufficient to compute a severity for each type of non-uniformity defect. The number of features extracted and the order in which the features are extracted is dynamically determined in real-time to reduce a cost associated with the feature extraction.Type: GrantFiled: October 28, 2011Date of Patent: May 12, 2015Assignee: 3M Innovative Properties CompanyInventors: Evan J. Ribnick, Kenneth G. Brittain, John A. Ramthun, Derek H. Justice, Guillermo Sapiro
-
Patent number: 9002072Abstract: A system is described for detecting the presence of non-uniformity patterns and providing output indicative of a severity of each type of non-uniformity pattern. The system includes a computerized rating tool that assists a user in efficiently and consistently assigning expert ratings (i.e., labels) to a large collection of training images representing samples of a given product. In addition, the rating software develops a model that allows a computerized inspection system to detect the presence of non-uniformity patterns in a manufactured web material in real time and provide output indicative of a severity level of each pattern on a continuous scale. The system also includes algorithmic and hardware approaches to significantly that increase the throughput of the inspection system.Type: GrantFiled: February 14, 2012Date of Patent: April 7, 2015Assignee: 3M Innovative Properties CompanyInventors: Catherine P. Tarnowski, Kenneth G. Brittain, David L. Hofeldt, Andrzej P. Jaworski, Gregory D. Kostuch, John A. Ramthun, Evan J. Ribnick, Esa H. Vilkama, Derek H. Justice, Guillermo Sapiro